{"url":"/dataset/ogb-lsc","name":"OGB-LSC","full_name":"OGB Large-Scale Challenge","description_markdown":"OGB Large-Scale Challenge (OGB-LSC) is a collection of three real-world datasets for advancing the state-of-the-art in large-scale graph ML. OGB-LSC provides graph datasets that are orders of magnitude larger than existing ones and covers three core graph learning tasks -- link prediction, graph regression, and node classification. \r\n\r\nOGB-LSC consists of three datasets: MAG240M-LSC, WikiKG90M-LSC, and PCQM4M-LSC. Each dataset offers an independent task.\r\n\r\n* MAG240M-LSC is a heterogeneous academic graph, and the task is to predict the subject areas of papers situated in the heterogeneous graph (node classification).\r\n* WikiKG90M-LSC is a knowledge graph, and the task is to impute missing triplets (link prediction).\r\n* PCQM4M-LSC is a quantum chemistry dataset, and the task is to predict an important molecular property, the HOMO-LUMO gap, of a given molecule (graph regression).","description_withheld":null,"homepage":"https://ogb.stanford.edu/kddcup2021/","introduced_date":"2021-03-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/ogb-lsc-a-large-scale-challenge-for-machine","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","first_author":"Weihua Hu","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Node Classification","url":"/task/node-classification","datasets_with_task":"/datasets/task/node-classification"},{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"},{"name":"Knowledge Graphs","url":"/task/knowledge-graphs","datasets_with_task":"/datasets/task/knowledge-graphs"},{"name":"Graph Regression","url":"/task/graph-regression","datasets_with_task":"/datasets/task/graph-regression"}],"languages":[],"variants":["OGB-LSC","MAG240M-LSC","WikiKG90M-LSC","PCQM4M-LSC"],"data_loaders":[],"num_papers_in_archive":34,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/graph-regression-on-pcqm4m-lsc","task":"Graph Regression","dataset_variant":"PCQM4M-LSC","rows":11,"metrics":["Test MAE","Validation MAE"],"first_row_in_archive_order":{"model":"Graphormer","paper":"/paper/do-transformers-really-perform-bad-for-graph","metrics":{"Test MAE":"13.28","Validation MAE":"0.1234"},"code_links":[{"title":"microsoft/Graphormer","url":"https://github.com/microsoft/Graphormer"},{"title":"Microsoft/Graphormer","url":"https://github.com/Microsoft/Graphormer"},{"title":"dpstart/graphormer_new","url":"https://github.com/dpstart/graphormer_new"},{"title":"ytchx1999/Graphormer","url":"https://github.com/ytchx1999/Graphormer/tree/main/examples/ogb"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/graphormer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/knowledge-graphs-on-wikikg90m-lsc","task":"Knowledge Graphs","dataset_variant":"WikiKG90M-LSC","rows":4,"metrics":["Test MRR","Validation MRR"],"first_row_in_archive_order":{"model":"TransE-Concat","paper":"/paper/ogb-lsc-a-large-scale-challenge-for-machine","metrics":{"Test MRR":"85.48","Validation MRR":"0.8494"},"code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/ogb_lsc"},{"title":"snap-stanford/ogb","url":"https://github.com/snap-stanford/ogb"},{"title":"graphcore/ogb-lsc-pcqm4mv2","url":"https://github.com/graphcore/ogb-lsc-pcqm4mv2"},{"title":"shamim-hussain/egt","url":"https://github.com/shamim-hussain/egt"},{"title":"graphcore/distributed-kge-poplar","url":"https://github.com/graphcore/distributed-kge-poplar"},{"title":"lars-research/3d-pgt","url":"https://github.com/lars-research/3d-pgt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/node-classification-on-mag240m-lsc","task":"Node Classification","dataset_variant":"MAG240M-LSC","rows":4,"metrics":["Test Accuracy","Validation Accuracy"],"first_row_in_archive_order":{"model":"R-GraphSAGE (NS)","paper":"/paper/ogb-lsc-a-large-scale-challenge-for-machine","metrics":{"Test Accuracy":"68.94"},"code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/ogb_lsc"},{"title":"snap-stanford/ogb","url":"https://github.com/snap-stanford/ogb"},{"title":"graphcore/ogb-lsc-pcqm4mv2","url":"https://github.com/graphcore/ogb-lsc-pcqm4mv2"},{"title":"shamim-hussain/egt","url":"https://github.com/shamim-hussain/egt"},{"title":"graphcore/distributed-kge-poplar","url":"https://github.com/graphcore/distributed-kge-poplar"},{"title":"lars-research/3d-pgt","url":"https://github.com/lars-research/3d-pgt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/graph-convolutions-enrich-the-self-attention","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","date":"2023-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":29,"samples_ran":19,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/graph-propagation-transformer-for-graph","title":"Graph Propagation Transformer for Graph Representation Learning","date":"2023-05-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/o-gnn-incorporating-ring-priors-into","title":"O-GNN: Incorporating Ring Priors into Molecular Modeling","date":"2023-05-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transformers-generalize-deepsets-and-can-be","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","date":"2021-10-27","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/edge-augmented-graph-transformers-global-self","title":"Global Self-Attention as a Replacement for Graph Convolution","date":"2021-08-07","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/do-transformers-really-perform-bad-for-graph","title":"Do Transformers Really Perform Bad for Graph Representation?","date":"2021-06-09","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/ogb-lsc-a-large-scale-challenge-for-machine","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","date":"2021-03-17","rows_on_this_dataset":13,"code_links":6,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":42,"samples_ran":23,"samples_unverified":19,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}